Intel Data Center GPU Flex 170 vs NVIDIA Jetson AGX Orin 32 GB
We compared two Professional market GPUs: 16GB VRAM Data Center GPU Flex 170 and 32GB VRAM Jetson AGX Orin 32 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Data Center GPU Flex 170 's Advantages
Boost Clock2050MHz
Larger VRAM bandwidth (512.0GB/s vs 204.8GB/s)
2304 additional rendering cores
NVIDIA Jetson AGX Orin 32 GB 's Advantages
Released 6 months late
More VRAM (32GB vs 16GB)
Lower TDP (40W vs 150W)
Score
Benchmark
FP32 (float)
Data Center GPU Flex 170
+403%
16.79 TFLOPS
Jetson AGX Orin 32 GB
3.333 TFLOPS
Graphics Card
Aug 2022
Release Date
Feb 2023
Data Center GPU
Generation
Tegra
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x4
Clock Speeds
1950 MHz
Base Clock
-
2050 MHz
Boost Clock
-
2000 MHz
Memory Clock
1600 MHz
Memory
16GB
Memory Size
32GB
GDDR6
Memory Type
LPDDR5
256bit
Memory Bus
256bit
512.0GB/s
Bandwidth
204.8GB/s
Render Config
-
-
-
-
SM Count
14
4096
Shading Units
1792
256
TMUs
56
128
ROPs
24
-
Tensor Cores
56
32
RT Cores
-
-
L1 Cache
128 KB (per SM)
16 MB
L2 Cache
256 KB
-
-
-
Theoretical Performance
262.4 GPixel/s
Pixel Rate
22.32 GPixel/s
524.8 GTexel/s
Texture Rate
52.08 GTexel/s
33.59 TFLOPS
FP16 (half)
6.666 TFLOPS
16.79 TFLOPS
FP32 (float)
3.333 TFLOPS
-
FP64 (double)
1.667 TFLOPS
Board Design
150W
TDP
40W
450 W
Suggested PSU
-
1x HDMI 2.1
3x DisplayPort 2.0
Outputs
Portable Device Dependent
1x 8-pin
Power Connectors
-
Graphics Processor
DG2-512
GPU Name
GA10B
ACM-G10
GPU Variant
-
Generation 12.7
Architecture
Ampere
TSMC
Foundry
Samsung
6 nm
Process Size
8 nm
21.7 billion
Transistors
Unknown
406 mm²
Die Size
Unknown
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
8.6
6.6
Shader Model
6.7
